What is codex-model-handoff?

A file-based workflow for handing coding tasks between Codex and DeepSeek through CCSwitch. It keeps plans, decisions, progress, and changes in project files so another model can continue the work.

Use it only for an explicit handoff workflow: initialize, plan, execute, capture changes, review, fix, complete, or check status.

It reduces lost context when switching models or sessions. The written handoff makes the current state and remaining work explicit.

codex-model-handoff — Skill for Claude Code and Codex by 1chen666

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add 1chen666/codex-handoff-skill-test-by-deepseek- --skill codex-model-handoff

Clone the repo

git clone --depth 1 https://github.com/1chen666/codex-handoff-skill-test-by-deepseek-

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/1chen666/codex-handoff-skill-test-by-deepseek-/codex-model-handoff/github.svg)](https://agentmods.dev/skills/1chen666/codex-handoff-skill-test-by-deepseek-/codex-model-handoff)

Your own site

<a href="https://agentmods.dev/skills/1chen666/codex-handoff-skill-test-by-deepseek-/codex-model-handoff"><img src="https://agentmods.dev/badge/skills/1chen666/codex-handoff-skill-test-by-deepseek-/codex-model-handoff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/1chen666/codex-handoff-skill-test-by-deepseek-/codex-model-handoff"><img src="https://agentmods.dev/badge/skills/1chen666/codex-handoff-skill-test-by-deepseek-/codex-model-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,541 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00100	$0.02541
Opus 5	$0.00050	$0.01270
Sonnet 5	$0.00020	$0.00508
Haiku 4.5	$0.00010	$0.00254

Measured 9d ago against content hash 8635dfac4845, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

codex-model-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

codex-model-handoff/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Model Handoff

This skill implements an explicit collaborative model handoff mode for Codex projects where GPT and DeepSeek are used through CCSwitch. It solves context continuity problems by writing task state into local project files instead of relying on Codex conversation history.

Activation Rule

Use this workflow only when the user explicitly invokes one of these forms:

/handoff
/handoff init
/handoff plan
/handoff execute
/handoff capture-diff
/handoff review
/handoff fix
/handoff complete
/handoff status
Use codex-model-handoff ...

If the user asks a normal coding question, requests a small edit, asks for an explanation, or mentions handoff concepts without explicitly invoking /handoff or Use codex-model-handoff, do not create or update handoff files and do not enforce this workflow.

In Chinese notes this may be described as "协作模式", but the actual command remains /handoff. Do not create or suggest Chinese slash command aliases such as /协作 or /交接.

Core Files

Use docs/handoff/ under the project root as the source of truth. Create it when needed.

Required files:

AGENTS.md
docs/handoff/handoff_state.md
docs/handoff/implementation_plan.md
docs/handoff/execution_log.md
docs/handoff/review_report.md
docs/handoff/decision_log.md
docs/handoff/git_status.txt
docs/handoff/diff_stat.txt
docs/handoff/current.diff

Keep handoff_state.md compact. Put detailed plans, execution records, review details, decisions, and Git evidence in the dedicated files.

Stage Preflight

For every handoff stage except status:

Treat the current working directory as the project root unless the user explicitly names another root.
Create docs/handoff/ if it is missing.
Create any missing required handoff files before doing stage-specific work.
Preserve unrelated existing content in AGENTS.md and handoff files unless the current stage explicitly updates that file.

Read the full file on GitHub · 301 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 301 lines · 100 tokens per session scan A 8635dfac4845

Subscribe to this mod's changes

codex-model-handoff is a skill published in the GitHub repository 1chen666/codex-handoff-skill-test-by-deepseek- (5 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 2,541 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

codex-model-handoff